Genetic Algorithm Based on Trip Priority Optimization and Its Application in Tourism Path Planning

ABSTRACT Current tourism path planning methods struggle to respond in real time to dynamic factors such as sudden changes in tourist flow and weather disturbances. Path adjustment delays often cause deviations from the optimal solution. To address these shortcomings, this study proposes a genetic algorithm based on trip priority optimization and introduces an improved ant colony optimization algorithm for further refinement. Experimental results show that the proposed model achieves over 90% time efficiency and parallel thread utilization at various tourist spots. The path planning model based on the improved ant colony optimization algorithm achieves a maximum parallel thread utilization rate of 78.25%. At the Mausoleum of the First Qin Emperor, the travel time of the proposed model is 6.03 min, while the path planning model combining ant colony optimization and genetic algorithms takes 7.86 min. The time without any path planning is 16.25 min. The path planning model based on the rapidly‐exploring random tree algorithm with a guiding function and the improved ant colony optimization algorithm has travel times of 12.84 and 13.25 min at the Mausoleum of the First Qin Emperor. In both the training and testing sets, the average solution quality of the proposed model significantly outperforms the comparison models. The highest average solution quality in the comparison models is only 74.56. The average solution quality of the proposed model in the training set ranges from 85.36 to 82.31. When the response time is 15 s, the path planning model based on ant colony optimization combined with genetic algorithms achieves average solution qualities of 76.51 and 75.34 in the training and testing sets. These results demonstrate that the proposed model is highly effective and robust in dynamic environments of tourist areas, providing decision support for smart tourism.